ML Engineer: LLM Integration, RAG & Guardrails

Netbell; United States; Remote; USD 110,000 - 170,000; Full time

Job summary

Netbell in the United States is seeking a middle-level ML Engineer to integrate large language models into products, optimize prompts, and assess response quality across metrics and human evaluation.

You will work within a microservice architecture, build retrieval-augmented generation systems, implement safety guardrails, and optimize inference while collaborating with product and ML teams to grow your skills under experienced leadership.

Qualifications

• Experience with large language models and their deployment in cloud environments.
• Experience integrating LLMs into products and optimizing prompts.
• Familiarity with microservice architectures and evaluation of model performance.

Responsibilities

• Integrate large language models into Netbell products and optimize prompts for quality.
• Evaluate response quality using metrics and human evaluation.
• Set up safety guardrails and monitoring for model outputs.
• Build retrieval-augmented generation systems and optimize inference processes.
• Collaborate with product and ML teams to drive improvements.

Skills

LLMs deployment

Cloud deployment

Prompt engineering

Evaluation metrics

Microservices

Tools

Python

PyTorch/TensorFlow

Docker

Kubernetes

RAG systems

Job description

Netbell in the United States is seeking a middle-level ML Engineer to integrate large language models into products, optimize prompts, and assess response quality across metrics and human evaluation.

You will work within a microservice architecture, build retrieval-augmented generation systems, implement safety guardrails, and optimize inference while collaborating with product and ML teams to grow your skills under experienced leadership.